Gemini CLI：配额和定价
¥Gemini CLI: Quotas and Pricing
Gemini CLI 提供了丰富的免费套餐，涵盖了众多个人开发者的用例。如果您需要企业/专业用途，或者需要更高的限额，则可以根据您使用的身份验证帐户类型，选择多种途径。
¥Gemini CLI offers a generous free tier that covers the use cases for many individual developers. For enterprise / professional usage, or if you need higher limits, there are multiple possible avenues depending on what type of account you use to authenticate.
看隐私和条款有关隐私政策和服务条款的详细信息。
¥See privacy and terms for details on Privacy policy and Terms of Service.
注意：公布的价格为标价；可能适用额外协商的商业折扣。
¥Note: published prices are list price; additional negotiated commercial discounting may apply.
本文概述了使用不同身份验证方法时适用于 Gemini CLI 的具体配额和定价。
¥This article outlines the specific quotas and pricing applicable to the Gemini CLI when using different authentication methods.
一般来说，有三个类别可供选择：
¥Generally, there are three categories to choose from:
免费使用：适合实验和轻度使用。
¥Free Usage: Ideal for experimentation and light use.
付费套餐（固定价格）：适用于需要更慷慨的每日配额和可预测成本的个人开发者或企业。
¥Paid Tier (fixed price): For individual developers or enterprises who need more generous daily quotas and predictable costs.
按需付费：对于专业用途、长期运行的任务或需要完全控制使用情况时来说，这是最灵活的选择。
¥Pay-As-You-Go: The most flexible option for professional use, long-running tasks, or when you need full control over your usage.
免费使用
¥Free Usage
您的旅程从慷慨的免费套餐开始，非常适合实验和轻度使用。
¥Your journey begins with a generous free tier, perfect for experimentation and light use.
您的免费使用限制取决于您的授权类型。
¥Your free usage limits depend on your authorization type.
使用 Google 登录（Gemini 个人代码辅助）
¥Log in with Google (Gemini Code Assist for Individuals)
适用于使用 Google 帐户进行身份验证以访问 Gemini Code Assist 个人版的用户。这包括：
¥For users who authenticate by using their Google account to access Gemini Code Assist for individuals. This includes:
1000 个模型请求/用户/天
¥1000 model requests / user / day
60 个模型请求/用户/分钟
¥60 model requests / user / minute
模型请求将根据 Gemini CLI 的决定在 Gemini 模型系列中进行。
¥Model requests will be made across the Gemini model family as determined by Gemini CLI.
了解更多信息双子座代码协助个人限制。
¥Learn more at Gemini Code Assist for Individuals Limits.
使用 Gemini API Key 登录（免费）
¥Log in with Gemini API Key (Unpaid)
如果您使用 Gemini API 密钥，还可以享受免费套餐。免费套餐包括：
¥If you are using a Gemini API key, you can also benefit from a free tier. This includes:
250 个模型请求/用户/天
¥250 model requests / user / day
10 个模型请求/用户/分钟
¥10 model requests / user / minute
模型请求仅针对 Flash 模型。
¥Model requests to Flash model only.
了解更多信息Gemini API 速率限制。
¥Learn more at Gemini API Rate Limits.
使用 Vertex AI 登录（快速模式）
¥Log in with Vertex AI (Express Mode)
Vertex AI 提供快速模式，无需启用计费。其中包括：
¥Vertex AI offers an Express Mode without the need to enable billing. This includes:
您需要提前 90 天启用计费功能。
¥90 days before you need to enable billing.
配额和模型是可变的，并且特定于您的帐户。
¥Quotas and models are variable and specific to your account.
了解更多信息Vertex AI Express 模式限制。
¥Learn more at Vertex AI Express Mode Limits.
付费等级：固定费用的更高限额
¥Paid tier: Higher limits for a fixed cost
如果您用完了初始请求数，则可以升级您的计划，以便继续使用 Gemini CLI，方法是使用Gemini Code Assist 的标准版或企业版通过注册这里配额和定价基于固定价格订阅，包含指定许可证席位。如需可预测费用，您可以使用 Google 登录。这包括：
¥If you use up your initial number of requests, you can upgrade your plan to continue to benefit from Gemini CLI by using the Standard or Enterprise editions of Gemini Code Assist by signing up here. Quotas and pricing are based on a fixed price subscription with assigned license seats. For predictable costs, you can log in with Google. This includes:
标准：
¥Standard:
1500 个模型请求/用户/天
¥1500 model requests / user / day
120 个模型请求/用户/分钟
¥120 model requests / user / minute
企业：
¥Enterprise:
2000 个模型请求/用户/天
¥2000 model requests / user / day
120 个模型请求/用户/分钟
¥120 model requests / user / minute
模型请求将根据 Gemini CLI 的决定在 Gemini 模型系列中进行。
¥Model requests will be made across the Gemini model family as determined by Gemini CLI.
了解更多信息Gemini Code Assist 标准版和企业版许可证限制。
¥Learn more at Gemini Code Assist Standard and Enterprise license Limits.
即用即付
¥Pay As You Go
如果您升级后仍达到每日请求限额或用尽 Gemini Pro 配额，最灵活的解决方案是切换到按量付费模式，即按实际使用的处理量付费。这是确保不间断访问的推荐方案。
¥If you hit your daily request limits or exhaust your Gemini Pro quota even after upgrading, the most flexible solution is to switch to a pay-as-you-go model, where you pay for the specific amount of processing you use. This is the recommended path for uninterrupted access.
为此，请使用 Gemini API 密钥或 Vertex AI 登录。
¥To do this, log in using a Gemini API key or Vertex AI.
Vertex AI（常规模式）：
¥Vertex AI (Regular Mode):
配额：由动态共享配额系统或预先购买的预配吞吐量控制。
¥Quota: Governed by a dynamic shared quota system or pre-purchased provisioned throughput.
成本：基于模型和令牌使用情况。
¥Cost: Based on model and token usage.
了解更多信息Vertex AI 动态共享配额和Vertex AI 定价。
¥Learn more at Vertex AI Dynamic Shared Quota and Vertex AI Pricing.
Gemini API 密钥：
¥Gemini API key:
配额：因定价层而异。
¥Quota: Varies by pricing tier.
成本：根据定价层和模型/令牌使用情况而有所不同。
¥Cost: Varies by pricing tier and model/token usage.
了解更多信息Gemini API 速率限制，Gemini API 定价
¥Learn more at Gemini API Rate Limits, Gemini API Pricing
需要强调的是，使用 API 密钥时，您需要按令牌/调用付费。对于令牌较少且调用次数较多的小型调用，这可能会更昂贵，但这是确保您的工作流程不受配额限制干扰的唯一方法。
¥It’s important to highlight that when using an API key, you pay per token/call. This can be more expensive for many small calls with few tokens, but it's the only way to ensure your workflow isn't interrupted by quota limits.
Google One 和 Ultra 计划、Gemini for Workspace 计划
¥Google One and Ultra plans, Gemini for Workspace plans
这些计划目前仅适用于基于 Google 体验的 Gemini 网页版产品（例如，Gemini 网页应用或 Flow 视频编辑器）。这些计划不适用于支持 Gemini CLI 的 API。我们正在积极考虑在未来支持这些计划。
¥These plans currently apply only to the use of Gemini web-based products provided by Google-based experiences (for example, the Gemini web app or the Flow video editor). These plans do not apply to the API usage which powers the Gemini CLI. Supporting these plans is under active consideration for future support.
避免高成本的技巧
¥Tips to Avoid High Costs
使用即用即付 API 密钥时，请注意使用情况以避免意外费用。
¥When using a Pay as you Go API key, be mindful of your usage to avoid unexpected costs.
不要盲目接受每条建议，特别是对于重构大型代码库等计算密集型任务。
¥Don't blindly accept every suggestion, especially for computationally intensive tasks like refactoring large codebases.
提示和命令要有针对性。你是按次付费的，所以要考虑如何以最有效的方式完成工作。
¥Be intentional with your prompts and commands. You are paying per call, so think about the most efficient way to get the job done.
Gemini API 与 Vertex
¥Gemini API vs. Vertex
Gemini API（gemini 开发者 api）：这是直接使用 Gemini 模型的最快方式。
¥Gemini API (gemini developer api): This is the fastest way to use the Gemini models directly.
Vertex AI：这是用于构建、部署和管理具有特定安全和控制要求的 Gemini 模型的企业级平台。
¥Vertex AI: This is the enterprise-grade platform for building, deploying, and managing Gemini models with specific security and control requirements.
了解您的使用情况
¥Understanding your usage
模型使用情况摘要可通过/stats命令并在会话结束时退出时显示。
¥A summary of model usage is available through the /stats command and presented on exit at the end of a session.